Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data

The accurate mapping of <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>) invasion is crucial for controlling its spread and reducing severe ecological problems. Satellite images have been extensively employed for <italic>S. alterniflora</ital...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiwei Ma, Li Zhuo, Jingjing Cao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10748369/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850066349227769856
author Yiwei Ma
Li Zhuo
Jingjing Cao
author_facet Yiwei Ma
Li Zhuo
Jingjing Cao
author_sort Yiwei Ma
collection DOAJ
description The accurate mapping of <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>) invasion is crucial for controlling its spread and reducing severe ecological problems. Satellite images have been extensively employed for <italic>S. alterniflora</italic> invasion monitoring; however, there are still several issues that need to be addressed. The spectral similarities between <italic>S. alterniflora</italic> and surrounding ground objects make it challenging for traditional classifiers to achieve satisfactory extraction accuracy. Since the phenological information and red-edge spectral differences have been considered as informative features for identifying <italic>S. alterniflora</italic>, current studies mainly used them separately as classification features and seldom considered the differences of red-edge information at different phenological periods. Therefore, we proposed a pixel-based phenological and red-edge feature composite method (PpRef-CM) for <italic>S. alterniflora</italic> extraction considering both phenological information and red-edge bands derived from Sentinel-2 time series based on the existing pixel-based phenological feature composite method (Ppf-CM). The proposed PpRef-CM and machine-learning algorithms were employed for <italic>S. alterniflora</italic> extraction in two typical mangrove forests along coastal China. Results indicated that red-edge information at different phenological periods is essential for detecting <italic>S. alterniflora</italic>. <italic>S. alterniflora</italic> extraction achieved the highest accuracy of 96.57&#x0025; by using the eXtreme gradient boost algorithm when compared with other machine-learning algorithms. The PpRef-CM gave 2.72&#x0025; and 2.61&#x0025; more extraction accuracies of <italic>S. alterniflora</italic> than the Ppf-CM in two study sites, separately. These findings provide insights for selecting suitable classification features for <italic>S. alterniflora</italic> extraction studies and serve as an effective control and management of <italic>S. alterniflora</italic>.
format Article
id doaj-art-462ea968aba247ef838ab5839aa55db7
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-462ea968aba247ef838ab5839aa55db72025-08-20T02:48:46ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118132410.1109/JSTARS.2024.349504810748369Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series DataYiwei Ma0https://orcid.org/0009-0009-6913-5740Li Zhuo1https://orcid.org/0000-0002-8780-7944Jingjing Cao2https://orcid.org/0000-0002-1239-2203Guangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaGuangdong Provincial Engineering Research Center for Public Security and Disaster, School of Geography and Planning, Sun Yat-sen University, Guangzhou, ChinaCollege of Computer Sciences, Guangdong Polytechnic Normal University, Guangzhou, ChinaThe accurate mapping of <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>) invasion is crucial for controlling its spread and reducing severe ecological problems. Satellite images have been extensively employed for <italic>S. alterniflora</italic> invasion monitoring; however, there are still several issues that need to be addressed. The spectral similarities between <italic>S. alterniflora</italic> and surrounding ground objects make it challenging for traditional classifiers to achieve satisfactory extraction accuracy. Since the phenological information and red-edge spectral differences have been considered as informative features for identifying <italic>S. alterniflora</italic>, current studies mainly used them separately as classification features and seldom considered the differences of red-edge information at different phenological periods. Therefore, we proposed a pixel-based phenological and red-edge feature composite method (PpRef-CM) for <italic>S. alterniflora</italic> extraction considering both phenological information and red-edge bands derived from Sentinel-2 time series based on the existing pixel-based phenological feature composite method (Ppf-CM). The proposed PpRef-CM and machine-learning algorithms were employed for <italic>S. alterniflora</italic> extraction in two typical mangrove forests along coastal China. Results indicated that red-edge information at different phenological periods is essential for detecting <italic>S. alterniflora</italic>. <italic>S. alterniflora</italic> extraction achieved the highest accuracy of 96.57&#x0025; by using the eXtreme gradient boost algorithm when compared with other machine-learning algorithms. The PpRef-CM gave 2.72&#x0025; and 2.61&#x0025; more extraction accuracies of <italic>S. alterniflora</italic> than the Ppf-CM in two study sites, separately. These findings provide insights for selecting suitable classification features for <italic>S. alterniflora</italic> extraction studies and serve as an effective control and management of <italic>S. alterniflora</italic>.https://ieeexplore.ieee.org/document/10748369/Invasive speciesphenologyred-edge bandsSentinel-2 time series<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$Spartina\ alterniflora$</tex-math> </inline-formula> </named-content> (<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$S.\ alterniflora$</tex-math> </inline-formula> </named-content>)
spellingShingle Yiwei Ma
Li Zhuo
Jingjing Cao
Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Invasive species
phenology
red-edge bands
Sentinel-2 time series
<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$Spartina\ alterniflora$</tex-math> </inline-formula> </named-content> (<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$S.\ alterniflora$</tex-math> </inline-formula> </named-content>)
title Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data
title_full Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data
title_fullStr Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data
title_full_unstemmed Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data
title_short Mapping Invasive <italic>Spartina alterniflora</italic> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data
title_sort mapping invasive italic spartina alterniflora italic using phenological information and red edge bands of sentinel 2 time series data
topic Invasive species
phenology
red-edge bands
Sentinel-2 time series
<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$Spartina\ alterniflora$</tex-math> </inline-formula> </named-content> (<named-content xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" content-type="math" xlink:type="simple"> <inline-formula> <tex-math notation="LaTeX">$S.\ alterniflora$</tex-math> </inline-formula> </named-content>)
url https://ieeexplore.ieee.org/document/10748369/
work_keys_str_mv AT yiweima mappinginvasiveitalicspartinaalternifloraitalicusingphenologicalinformationandrededgebandsofsentinel2timeseriesdata
AT lizhuo mappinginvasiveitalicspartinaalternifloraitalicusingphenologicalinformationandrededgebandsofsentinel2timeseriesdata
AT jingjingcao mappinginvasiveitalicspartinaalternifloraitalicusingphenologicalinformationandrededgebandsofsentinel2timeseriesdata